KEYWORDS: Image segmentation, Mammography, Solid modeling, Computer aided diagnosis and therapy, Digital mammography, Computer programming, Breast cancer, Visual process modeling, Databases, Detection and tracking algorithms
Mammographic mass segmentation plays a crucial role in
computer-aided scheme (CAD). In this paper, we propose a
method based on maximum entropy principle and active contour model to do segmentation. There are two main steps in
this method. First, maximum entropy principle was applied on the background-trend corrected regions of interest (ROIs) to
obtain the initially detected outlines. Secondly, active contour model was used to refine the initially detected outlines of the
masses. The regions of interest used in this study were extracted from images in the Digital Database for Screening
Mammography (DDSM) provided by the University of South Florida. The preliminary experimental results are
encouraging. The segmentation algorithm performs robustly and well for various types of masses. The overlap criterion
analysis shows that the proposed segmentation results are more similar to radiologists' manual segmentation compared
with other experimented methods.
KEYWORDS: Breast, Mammography, Image segmentation, Computer aided diagnosis and therapy, Tumors, Digital mammography, Computer programming, Tissues, Databases, Breast cancer
In clinic, surrounding density of breast abnormalities is an important cue for radiologists to distinguish between benign
and malignant abnormalities on mammogram. It may also be an important feature to be used in computer-aided diagnosis
(CAD) system. The purpose of our work is to analyze the density distribution surrounding benign or malignant mass.
The cases used in this study are selected from the Digital Database for Screening Mammography (DDSM) provided by
the University of South Florida. For each case, the mass boundaries marked by experienced radiologists are used and 30
3-pixel-wide bands, one outside another, surrounding each mass are considered. A few density features including the
average gray level and the distribution skewness of the gray levels on every surrounding band were calculated. For every
feature in each corresponding band, average values were calculated for 10 benign cases and 10 malignant cases,
respectively. The preliminary analysis results show that the intensities surrounding benign masses tend to be higher than
those surrounding malignant masses. They also show that the standard deviation of intensities surrounding benign
masses tend to be larger than those surrounding malignant masses. Similar analysis was also carried out with mass
boundaries automatically identified by computer and the results corroborate the analysis with mass boundaries marked
by radiologists.
KEYWORDS: Databases, Mammography, CAD systems, Prototyping, Image retrieval, Content based image retrieval, Computer aided diagnosis and therapy, Pathology, Breast cancer
A method for computer-aided detection (CAD) of mammographic masses is proposed and a prototype CAD system is
presented. The method is based on content-based image retrieval (CBIR). A mammogram database containing 2000
mammographic regions is built in our prototype CBIR-CAD system. Every region of interested (ROI) in the database has
known pathology. Specifically, there are 583 ROIs depicting biopsy-proven masses, and the rest 1417 ROIs are normal.
Whenever a suspicious ROI is detected in a mammogram by a radiologist, it can be submitted as a query to this CBIRCAD
system. As the query results, a series of similar ROI images together with their known pathology knowledge will
be retrieved from the database and displayed in the screen in descending order of their similarities to the query ROI to
help the radiologist to make the diagnosis decision. Furthermore, our CBIR-CAD system will output a decision index
(DI) to quantitatively indicate the probability that the query ROI contains a mass. The DI is calculated by the query
matches. In the querying process, 24 features are extracted from each ROI to form a 24-dimensional vector. Euclidean
distance in the 24-dimensional feature vector space is applied to measure the similarities between ROIs. The prototype
CBIR-CAD system is evaluated based on the leave-one-out sampling scheme. The experiment results showed that the
system can achieve a receiver operating characteristic (ROC) area index AZ =0.84 for detection of mammographic
masses, which is better than the best results achieved by the other known mass CAD systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.